+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Optimization & Performance (https://www.datasculpting.ai/inference/forumdisplay.php?fid=10)
+--- Forum: Context / KV Cache (https://www.datasculpting.ai/inference/forumdisplay.php?fid=41)
+--- Thread: prefix caching on repeated workflows (/showthread.php?tid=488)
prefix caching on repeated workflows - tensorriver - 09-25-2026
Posting this in case it saves someone else a little time.
I'm not trying to build a perfect architecture diagram. I just want a sane starting point around vLLM and 7900 XTX.
Would rather learn from your scars than collect my own all at once.
Re: prefix caching on repeated workflows - vramscope - 09-27-2026
That matches what I was seeing. The pattern around quant drift has been pretty similar for me.
Re: prefix caching on repeated workflows - cacheline - 09-28-2026
A couple questions before I guess too hard. Are you testing this on mini PC or something else?